CVPR 2017 accepted papers on Video
101 of the 783 papers accepted at CVPR 2017 (12.9%) are on Video, compared with 10.7% at CVPR 2016. They fall into 3 topics.
See CVPR 2017 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Video segmentation and tracking · 52 papers
- One-Shot Video Object Segmentation (926 citations)
- End-To-End Learning of Driving Models From Large-Scale Video Datasets (879 citations)
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (800 citations)
- Unsupervised Video Summarization With Adversarial LSTM Networks (637 citations)
- GMS: Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence (618 citations)
- Deep Video Deblurring for Hand-Held Cameras (607 citations)
- Video Frame Interpolation via Adaptive Convolution (533 citations)
- Neural Aggregation Network for Video Face Recognition (420 citations)
- FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (381 citations)
- Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization (350 citations)
- See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification (348 citations)
- Learning Motion Patterns in Videos (290 citations)
and 40 more in the interactive map.
Action recognition · 33 papers
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (9,707 citations)
- Temporal Convolutional Networks for Action Segmentation and Detection (2,175 citations)
- A New Representation of Skeleton Sequences for 3D Action Recognition (789 citations)
- Spatiotemporal Multiplier Networks for Video Action Recognition (713 citations)
- Deep Feature Flow for Video Recognition (688 citations)
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos (608 citations)
- UntrimmedNets for Weakly Supervised Action Recognition and Detection (586 citations)
- ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification (528 citations)
- SST: Single-Stream Temporal Action Proposals (476 citations)
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (466 citations)
- Self-Supervised Video Representation Learning With Odd-One-Out Networks (454 citations)
- Deep Representation Learning for Human Motion Prediction and Classification (421 citations)
and 21 more in the interactive map.
Video-language understanding · 16 papers
- Lip Reading Sentences in the Wild (613 citations)
- Video Captioning With Transferred Semantic Attributes (378 citations)
- End-To-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering (228 citations)
- Tracking by Natural Language Specification (186 citations)
- Automatic Understanding of Image and Video Advertisements (163 citations)
- Top-Down Visual Saliency Guided by Captions (144 citations)
- Hierarchical Boundary-Aware Neural Encoder for Video Captioning (141 citations)
- Query-Focused Video Summarization: Dataset, Evaluation, and a Memory Network Based Approach (138 citations)
- Weakly Supervised Dense Video Captioning (136 citations)
- A Dataset and Exploration of Models for Understanding Video Data Through Fill-In-The-Blank Question-Answering (86 citations)
- Collaborative Summarization of Topic-Related Videos (81 citations)
- Supervising Neural Attention Models for Video Captioning by Human Gaze Data (75 citations)
and 4 more in the interactive map.
